A method of measuring working distance between a handheld digital device and eyes of a user, including capturing an image of at least eyes of a user via an onboard camera of the handheld digital device while the user is viewing a display of the handheld digital device and comparing an apparent angular size of a structure of the eyes or face of the user to a previously captured image of the structure of the eyes or the face that was taken in the presence of an object of known size. The method further includes calculating a working distance based on the apparent angular size of the structure of the eyes or the face; and saving at least the working distance to memory or reporting out the calculated working distance on the display. A handheld digital device programmed with an algorithm to perform the method is also included.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The computer implemented method as claimed in claim 1, further comprising calibrating a processor of the handheld digital device by capturing an image of eye structures, facial structures or both while including an object of known size in the captured image.
3. The computer implemented method as claimed in claim 2, further comprising measuring a size of the eye structures, facial structures or both relative to the object of known size in the captured image.
This invention relates to computer vision techniques for analyzing images to determine the size of eye structures, facial structures, or both relative to an object of known size within the same captured image. The method involves capturing an image containing both a subject and an object of known dimensions, then processing the image to identify and measure the subject's eye structures, facial features, or both. By comparing these measurements to the known dimensions of the object, the system calculates the relative size of the subject's anatomical features. This approach enables precise scaling of facial and ocular measurements without requiring direct physical measurements or specialized equipment. The technique is useful in applications such as medical diagnostics, biometric analysis, and augmented reality, where accurate size relationships between facial features and reference objects are critical. The method leverages image processing algorithms to detect and quantify structural dimensions, ensuring reliable and repeatable results across different imaging conditions. By integrating this measurement step into the broader image analysis process, the system provides a comprehensive solution for deriving anatomical size data from standard images.
4. The computer implemented method as claimed in claim 1, further comprising measuring the working distance directly or on the basis of comparison to the object of known size.
5. The computer implemented method as claimed in claim 1, further comprising calculating a Snellen visual acuity or a Snellen visual acuity equivalent and transmitting the Snellen visual acuity or the Snellen visual acuity equivalent to the health care practitioner.
6. The computer implemented method as claimed in claim 3, further comprising measuring the working distance while reading material is read based on the previously measured size of eye structures or facial structures.
This invention relates to computer vision systems for measuring working distance in reading applications. The problem addressed is accurately determining the distance between a user and reading material, such as a book or screen, to optimize readability and reduce eye strain. Traditional methods often rely on fixed sensors or manual adjustments, which lack precision and adaptability. The method involves using computer vision techniques to analyze eye structures or facial features captured by an imaging device. By measuring the size of these structures in the captured images, the system calculates the working distance between the user and the reading material. This measurement is then used to adjust display settings, such as font size or screen brightness, to improve readability. The system continuously updates the working distance as the user moves, ensuring consistent readability. The method leverages pre-calibrated data on the typical size of eye or facial structures to estimate distance. For example, if the system detects that the pupil appears smaller than expected, it infers that the user has moved farther away and adjusts accordingly. This approach eliminates the need for additional distance sensors, reducing hardware complexity and cost. The invention is particularly useful in digital reading devices, such as e-readers or tablets, where maintaining an optimal reading distance is critical for user comfort. By dynamically adjusting settings based on real-time measurements, the system enhances the reading experience while minimizing eye fatigue. The method can also be applied in augmented reality (AR) or virtual reality (VR) environments where precise distance measurements are essential for immersive content display.
7. The computer implemented method as claimed in claim 1, further comprising saving additional information to memory selected from a group consisting of time, date, lighting conditions, display brightness, pupil size, whether the user is wearing corrective lenses at the time of recording and a combination of the foregoing.
8. The computer implemented method as claimed in claim 1, further comprising analyzing a captured image of the user to determine if corrective lenses are worn at a time of the measuring of working distance.
This describes a specific feature of a computer-implemented method, executed on a handheld digital device, for determining a user's working distance (the main invention described in Claim 1, inferred from the patent title and other claims). As part of this overall working distance measurement process, the method includes capturing an image of the user. This captured image is then analyzed by the device to determine whether the user is wearing corrective lenses (like glasses or contact lenses) at the exact moment the working distance is being measured. This allows the system to log the user's lens-wearing status alongside the working distance data. ERROR (embedding): Error: Failed to save embedding: Could not find the 'embedding' column of 'patent_claims' in the schema cache
9. The computer implemented method as claimed in claim 8, further comprising recording status as to whether the corrective lenses are worn and transmitting the status as to whether corrective lenses are a worn to the health care practitioner.
10. The computer implemented method as claimed in claim 1, further comprising analyzing a captured image to determine a pupil size; and optionally, transmit information of the pupil size to a health care practitioner.
This invention relates to computer-implemented methods for analyzing pupil size from captured images, particularly in the context of health monitoring. The method involves capturing an image of a user's eye and processing the image to determine the pupil size. The pupil size data can then be transmitted to a healthcare practitioner for further analysis. This technology addresses the need for automated, non-invasive monitoring of pupil size, which is a critical indicator of neurological and physiological health. By integrating image processing and data transmission, the method enables remote or real-time assessment of pupil size, improving diagnostic capabilities and patient monitoring. The system may include additional features such as image preprocessing to enhance accuracy, pupil detection algorithms, and secure data transmission protocols to ensure privacy and reliability. The method is particularly useful in medical applications where continuous or periodic pupil size monitoring is required, such as in neurological assessments, anesthesia monitoring, or concussion evaluation. The invention provides a technical solution for automating pupil size measurement, reducing human error, and enabling remote healthcare interventions.
11. The computer implemented method as claimed in claim 1, further comprising presenting an optokinetic stimulus of moving bars, stripes or a checkerboard on the display of the handheld digital device; and capturing moving images of eye movements that occur in response to the optokinetic stimulus.
This invention relates to a computer-implemented method for analyzing eye movements in response to visual stimuli, particularly using a handheld digital device. The method addresses the challenge of accurately tracking eye movements in a portable, user-friendly manner, which is useful for applications in vision research, medical diagnostics, or user interface design. The method involves presenting an optokinetic stimulus—a visual pattern such as moving bars, stripes, or a checkerboard—on the display of a handheld digital device. This stimulus triggers involuntary eye movements, which are then captured as moving images using the device's camera or other imaging system. The captured eye movement data can be analyzed to assess visual tracking performance, detect abnormalities, or evaluate user interaction with the device. The method may also include preprocessing the captured images to enhance tracking accuracy, such as adjusting for lighting conditions or device orientation. The system may further process the eye movement data to extract metrics like saccade frequency, smooth pursuit velocity, or fixation duration, providing insights into visual processing or neurological function. By leveraging the built-in capabilities of handheld devices, this approach enables portable, cost-effective eye movement analysis without specialized equipment, making it accessible for clinical, research, or consumer applications.
12. The computer implemented method as claimed in claim 11, further comprising analyzing the moving images of eye movements in response to the optokinetic stimulus; and, optionally, transmitting the moving image of eye movements, the analysis of eye movements or both to a health care practitioner.
13. The computer implemented method as claimed in claim 1, further comprising measuring the working distance by a depth mapping process using projected patterns including projecting an illuminated pattern of multiple spots onto the face of the user.
This invention relates to computer vision systems for facial recognition or tracking, specifically addressing the challenge of accurately determining the working distance between a user's face and a camera. The method involves projecting an illuminated pattern of multiple spots onto the user's face and analyzing the reflected light to generate a depth map. This depth mapping process enables precise measurement of the distance between the camera and the user's face, improving the accuracy of facial recognition or tracking systems. The projected pattern may include structured light or other optical markers that deform when reflected off the face, allowing the system to calculate depth based on the distortion of the pattern. This technique enhances performance in applications such as augmented reality, biometric authentication, or user interface interactions where distance measurement is critical. The method may be integrated into existing facial recognition systems to provide real-time distance feedback, ensuring reliable operation across varying environmental conditions. The use of projected patterns improves accuracy compared to passive depth-sensing methods, particularly in dynamic or low-light scenarios. The system may also compensate for facial movements or occlusions by continuously updating the depth map, maintaining consistent performance. This approach is particularly useful in consumer electronics, security systems, and human-computer interaction applications where precise spatial awareness is required.
14. The computer implemented method as claimed in claim 1, further comprising creating a depth map of the user's face including a matrix of pixels wherein each pixel corresponds to respective location on the face and includes a respective pixel value indicative of a distance from a reference location at the handheld digital device to respective location pixel.
15. The computer implemented method as claimed in claim 14, further comprising using the depth map to identify a contour of the user's face representing the users eyes or a bridge of a user's nose to measure a distance between the users eyes or the users bridge of the nose and the handheld digital device.
This invention relates to computer vision techniques for measuring distances between a user's facial features and a handheld digital device. The method addresses the challenge of accurately determining spatial relationships between a user's face and a device, such as a smartphone or tablet, to improve applications like augmented reality, facial recognition, or user interface adjustments. The system captures an image of the user's face and generates a depth map, which represents the three-dimensional structure of the face. The depth map is analyzed to identify specific facial contours, such as the user's eyes or the bridge of the nose. These contours are used to calculate the distance between the user's eyes or the bridge of the nose and the handheld device. The method may also involve tracking the user's head movements to refine distance measurements over time. By leveraging depth sensing and facial feature detection, the system enables precise spatial awareness for enhanced device interactions. This approach improves accuracy in applications requiring proximity-based adjustments or spatial context, such as virtual object placement or adaptive display settings.
16. The computer implemented method as claimed in claim 14, further comprising receiving color image data at a first input port including a first array of color image pixels from a first image sensor; receiving depth related image data at a second input port from a second image sensor and processing the depth related image data to generate a depth map.
18. The handheld digital device as claimed in claim 17, further wherein the image analysis engine is further programmed to use an apparent size of structures of users face and eyes; and to calculate the working distance between display and the user's eyes from the apparent size.
This invention relates to a handheld digital device with an image analysis engine that determines the working distance between the device's display and a user's eyes. The device includes a camera for capturing images of the user's face and eyes, and the image analysis engine processes these images to analyze the apparent size of facial structures, particularly the eyes. By comparing the apparent size of these structures to known reference sizes, the engine calculates the distance between the display and the user's eyes. This functionality enables the device to adjust display settings, such as brightness or focus, based on the user's proximity to optimize viewing conditions. The system may also use additional facial features or eye tracking to refine distance calculations. The invention addresses the need for dynamic display adjustments in handheld devices to enhance user experience and reduce eye strain. The image analysis engine operates in real-time, continuously updating the working distance as the user moves the device. This ensures consistent display performance regardless of the user's position relative to the screen. The technology is particularly useful in smartphones, tablets, and other portable devices where screen-to-eye distance varies frequently.
19. The handheld digital device as claimed in claim 17, further wherein the image analysis engine is further programmed to save additional information to memory selected from a group consisting of time, date, lighting conditions, display brightness, pupil size, whether the user is wearing corrective lenses at the time of recording and a combination of the foregoing.
20. The handheld digital device as claimed in claim 17, further wherein the image analysis engine is programmed to measure the working distance by a depth mapping process using projected patterns including projecting an illuminated pattern of multiple spots onto the face of the user.
21. The handheld digital device as claimed in claim 17, further wherein the image analysis engine is programmed to create a depth map of the user's face including a matrix of pixels wherein each pixel corresponds to respective location on the face and includes a respective pixel value indicative of a distance from a reference location at the handheld digital device to respective location pixel.
22. The handheld digital device as claimed in claim 21, further wherein the image analysis engine is programmed to analyze the depth map to identify a contour representing the users eyes or a bridge of a user's nose to measure a distance between the users eyes or the users bridge of the nose and the handheld digital device.
24. The handheld digital device as claimed in claim 23, wherein the image capture engine further comprises a first input port the receives color image data and thus including a first array of color image pixels from a first image sensor and a second port the receives depth related image data from a second image sensor and processing circuitry that generates a depth map using the depth related image data.
A handheld digital device captures and processes both color and depth image data to generate a depth map. The device includes an image capture engine with two input ports: one for receiving color image data from a first image sensor, which provides a color pixel array, and another for receiving depth-related image data from a second image sensor. Processing circuitry within the engine uses the depth-related data to generate a depth map, which represents spatial information about objects in the captured scene. This allows the device to analyze and interpret three-dimensional environments, enabling applications such as augmented reality, object recognition, and spatial mapping. The integration of color and depth data enhances the device's ability to accurately reconstruct and interact with real-world scenes, improving functionality in areas like navigation, gaming, and robotics. The system ensures synchronized processing of both data streams to maintain spatial coherence between color and depth information.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 29, 2018
November 8, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.